Range estimation via multidimensional segmentation

A new graph-theoretic algorithm for stereo range estimation, utilizing a Mumford-Shah variational, multidimensional segmentation of a 3D or 4D spatio-(temporal)-parallax space to implicitly solve the stereo correspondence problem, is described. Initial results and comparison with an area correlation...

Full description

Saved in:
Bibliographic Details
Main Author: Parker, B.
Format: Conference Proceeding
Language:English
Subjects:
Australia
Cameras
Image segmentation
Information technology
Iterative algorithms
Multidimensional systems
Object recognition
Optical distortion
Space technology
Stereo image processing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A new graph-theoretic algorithm for stereo range estimation, utilizing a Mumford-Shah variational, multidimensional segmentation of a 3D or 4D spatio-(temporal)-parallax space to implicitly solve the stereo correspondence problem, is described. Initial results and comparison with an area correlation range estimation algorithm demonstrate that it is capable of producing very accurate boundary demarcation including alpha coverage information, suggesting its applicability to foreground/background separation and range keying applications.
ISSN:1522-4880
2381-8549
DOI:10.1109/ICIP.2003.1247132